{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:37SVAJFUXCHQJ5RGKK6OO5PN53","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56c1d2168f21888450731580e589cc3e565f8b33c02e143f650cfde24b408f5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:59:38Z","title_canon_sha256":"d1ab1ea376493ab6e3b97d5eabefd00860e75077fd6748c7cf8567c57d435efd"},"schema_version":"1.0","source":{"id":"2506.08933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08933","created_at":"2026-07-05T11:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08933v1","created_at":"2026-07-05T11:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08933","created_at":"2026-07-05T11:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"37SVAJFUXCHQ","created_at":"2026-07-05T11:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"37SVAJFUXCHQJ5RG","created_at":"2026-07-05T11:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"37SVAJFU","created_at":"2026-07-05T11:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:f0dce0e62cbca513f29d2e6780e9a31c1320e7e9dd9e58dc121fbd34755dba3b","target":"graph","created_at":"2026-07-05T11:19:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.08933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual annotation with limited scenarios, and a lack of multidimensional evaluation. In response to these challenges, we introduce OmniBench, a self-generating, cross-platform, graph-based benchmark with an automated pipeline for synthesizing tasks of controllable complexity through subtask composition. To evaluate the diverse capabilities of virtual agents on the g","authors_text":"Bingchen Miao, Juncheng Li, Kaihang Pan, Mengze Li, Minghe Gao, Qifan Yu, Siliang Tang, Wei Ji, Wendong Bu, Yang Wu, Yueting Zhuang, Yunfei Li, Zhenkui Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:59:38Z","title":"What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08933","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:10573f45399aca61a3e43bd8c2eaf2c61e066e235517ca8a75ee8322ce0e9dda","target":"record","created_at":"2026-07-05T11:19:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56c1d2168f21888450731580e589cc3e565f8b33c02e143f650cfde24b408f5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:59:38Z","title_canon_sha256":"d1ab1ea376493ab6e3b97d5eabefd00860e75077fd6748c7cf8567c57d435efd"},"schema_version":"1.0","source":{"id":"2506.08933","kind":"arxiv","version":1}},"canonical_sha256":"dfe55024b4b88f04f62652bce775edeee6b5e8a426be417d19514e7592c200d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfe55024b4b88f04f62652bce775edeee6b5e8a426be417d19514e7592c200d0","first_computed_at":"2026-07-05T11:19:15.373448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:15.373448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXX2xz/NUEqCvBPL/AO7RNd2dHvB6r0EDK+R3kb6Bh9vsPrwAegf+6gvpzKbNqpxwwNRm0ubsvjBQ9Bw/0wAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:15.374025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10573f45399aca61a3e43bd8c2eaf2c61e066e235517ca8a75ee8322ce0e9dda","sha256:f0dce0e62cbca513f29d2e6780e9a31c1320e7e9dd9e58dc121fbd34755dba3b"],"state_sha256":"a089d5eb77efae2cf60151fe6a887457924bf98a00c21d4d7751ec84503d6c3d"}